Starling-LM-7B-alpha-ExPO: benchmark results
Provider: UC Berkeley. Released 2024-04-26. Access: Open.
Aggregate Rating 1410 ± 24, rank #5620 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 61.56 | Accuracy (%) (5-shot) | 74.3 |
| Open LLM Leaderboard v1 - MMLU | 64.64 | Accuracy (%) (5-shot) | 74 |
| Open LLM Leaderboard v1 - WinoGrande | 80.35 | Accuracy (%) (5-shot) | 73.5 |
| Open LLM Leaderboard v1 - HellaSwag | 84.79 | Normalized accuracy (%) (10-shot) | 68.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 63.91 | Normalized accuracy (%) (25-shot) | 64.8 |
| AlpacaEval 2.0 | 19.47 | LC Win Rate (%) | 49.1 |
| Open Chinese LLM - GSM8K | 37.53 | Accuracy (%) | 34.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 46.38 | MC2 (%) (0-shot) | 34.3 |
| Open Chinese LLM - TruthfulQA MC | 50.86 | Accuracy (%) | 23.7 |
| Open Chinese LLM Leaderboard | 51.28 | Official Nonzero-Task Mean (%) | 21.6 |
| Open Chinese LLM - ARC Challenge | 46.25 | Accuracy (%) | 21 |
| Open Chinese LLM - HellaSwag | 53.32 | Accuracy (%) | 14.5 |
Interactive version: theaggregate.ai/model?slug=starling-lm-7b-alpha-expo · How It Works · Data refreshed daily, snapshot 2026-11-08.